Exploring Gender Disparities in Automatic Speech Recognition Technology
This research addresses fairness issues in ASR technology for users across genders, but it is incremental as it builds on existing studies of bias in speech recognition.
The study investigated how gender disparities in training data affect fairness and performance in Automatic Speech Recognition (ASR) systems, finding that optimal fairness occurs at specific gender distributions rather than a 50-50 split, with factors like pitch variability significantly impacting accuracy.
This study investigates factors influencing Automatic Speech Recognition (ASR) systems' fairness and performance across genders, beyond the conventional examination of demographics. Using the LibriSpeech dataset and the Whisper small model, we analyze how performance varies across different gender representations in training data. Our findings suggest a complex interplay between the gender ratio in training data and ASR performance. Optimal fairness occurs at specific gender distributions rather than a simple 50-50 split. Furthermore, our findings suggest that factors like pitch variability can significantly affect ASR accuracy. This research contributes to a deeper understanding of biases in ASR systems, highlighting the importance of carefully curated training data in mitigating gender bias.